Negotiation Research, Based On Multi-agent Learning

In recent years, Agent and Multi-Agent System (MAS) is growing up to be one of the most important techniques in the practical research on Artificial Intelligence and intelligent software in distributed computing environment. In the literature of MAS there are three main categories, known as Agent behavior theory, Agent architecture and collaboration among Agents that is focused on how Agents can effectively interact, notably negotiation, as a useful mechanism to get a beneficial result for both sides in the course of collaboration, becoming more inviting to researchers.Researchers use many methods to enhance Agent's adaptability and decision-making capacity in the research of MAS negotiation model. Learning algorithms was one of most important methods which was added to the MAS negotiation models to enable improved system performance. However, the current Learning algorithms of the Agent negotiation exist only in the process of the negotiation. The Agents also lack for knowledge about their opponents before negotiation.At first, the Concept of consultation and negotiation process of MAS and types of negotiation was detailed analyzed in this paper. Feasibility analysis about enhancing the ability of the Agent decision-making model was showed after the survey of the existing learning algorithms and decision-making models.Agents own decision-making efficiency and ultimately benefits is affected by the knowledge that they know about their opponents before negotiation. In this paper, opponent's reserve values of multi-issues were forecast by analyzing negotiation history based Bayesian theory, where the learning schemes of the Agent negotiation of Zeng and Sycara(1998) was referenced. Then, we improve the negotiation model to enhance Agenfs ultimately benefits according to the forecast results. The performance of improved model was proved by experiments.Opponent's strategies were forecast by analyzing negotiation history based...